Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- worldkit
|
| 5 |
+
- world-model
|
| 6 |
+
- jepa
|
| 7 |
+
- robotics
|
| 8 |
+
- push-t
|
| 9 |
+
library_name: worldkit
|
| 10 |
+
pipeline_tag: reinforcement-learning
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# WorldKit / Push-T (Default)
|
| 14 |
+
|
| 15 |
+
The default Push-T world model for [WorldKit](https://github.com/DilpreetBansi/worldkit).
|
| 16 |
+
This is the `base` config (13M params, 192-D latent space).
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from worldkit import WorldModel
|
| 20 |
+
|
| 21 |
+
model = WorldModel.from_hub("DilpreetBansi/pusht")
|
| 22 |
+
plan = model.plan(current_frame, goal_frame)
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
See [DilpreetBansi/pusht-base](https://huggingface.co/DilpreetBansi/pusht-base) for full details.
|
| 26 |
+
|
| 27 |
+
Built by [Dilpreet Bansi](https://github.com/DilpreetBansi).
|